DBPapers

A STUDY ON GENERATION METHODOLOGY OF AN INDOOR NETWORK USING BUILDING EVACUATION MAP

S. Park, S. Kim, K. Yu
Thursday 11 October 2018 by Libadmin2018

ABSTRACT

The demand for an indoor navigation service is increasing as indoor positioning technology is developed, therefore it is necessary to construct indoor network data that can be directly used for navigation. In this study, indoor network data were constructed using indoor evacuation map images, which can be easily obtained. The evacuation route in the map can be used as network information because it represents the connection between each room as well as the connection between room entrances and the main entrance of the floor. The indoor network defined in this study is composed of nodes of entrance and links indicating the connections between entrances. A conditional generative adversarial network (GAN) was used to extract information about door locations and evacuation routes from the evacuation map images, and door locations were converted into point data. Through vector conversion, evacuation route information was saved as polyline data. The generated door points and evacuation route lines were overlaid with the existing indoor wall data to generate network data for each floor. Through the proposed method, it is possible to generate network data that can be directly used for a navigation service by using the existing building evacuation information constructed already. It is expected that the indoor network data will be automatically generated through a large amount of image data that can be easily obtained by utilizing research results.

Keywords: indoor network, building evacuation map, indoor spatial information


Home | Contact | Site Map | Site statistics | Visitors : 0 / 353063

Follow site activity en  Follow site activity GEOINFORMATICS  Follow site activity Papers SGEM2018   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge
   

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License